Rubric-Guided Generation

Follow this topic Ask about this topic

Rubric-guided generation studies how to turn a request into explicit criteria, such as coverage, factual support, or style, and use them to assess outputs and guide models toward better ones. Methods include preference- and expert-grounded rubric induction, retrieval and consensus, and adaptive or adversarial refinement; criteria can then serve as rewards for reinforcement learning, step-level feedback, or token-level distillation. Applications range from research reports and medical answers to reasoning, essays, code, visual design, and music. Rubrics can provide finer learning signals than scalar rewards, but automatically generated criteria may still miss expert standards, be misweighted, or be gamed, making reliability, calibration, and efficient validation central challenges.

Latest papers

42 papers7 papers in the last four weeks, up 75% on the four weeks before. 0.0% of all new papers.

RubricOpt: Self-Revision of Semantic Rubrics for Preference Optimization
Oct 21, 2026Wei Chen, Yubing Wu, Shigui Li +7Rubric-Guided Generation Preference Optimization
South China University of Technology · LinkSprite · University of Waterloo
From Structure to Validity: Mechanism-Guided Generation and Refinement of LLM Rubrics
Oct 9, 2026Feifei Qian, Xuan Chen, Lixin Cui +6Automatic Rubric Generation Rubric-Based Evaluation
School of Artificial Intelligence, Beijing Normal University · KE Holdings Inc. · School of Information, Central University of Finance and Economics
Rubric-Based Optimization for Text-to-Music Generation
Oct 2, 2026Ping Wang, Guang Yang, Shao-Rong Su +3Text-to-Music Generation Rubric-Based RL
Paul G. Allen School of Computer Science & Engineering, University of Washington · Department of Electrical and Computer Engineering, University of Washington · Allen Institute for AI
Scoring Higher, Answering Worse: Mitigating Reward Hacking in Rubric-Based RL via Protocol-Level Rubrics
Sep 30, 2026Maoqi Liu, Junwei He, Bowen Zhang +5Reward Hacking Rubric-Based RL
Beijing University of Posts and Telecommunications · ByteDance
Mubric: Mutation Testing-Guided Rubric Generation for LLM Evaluation
Sep 29, 2026Jiayuxuan Yang, Jie M. Zhang, Yiling Lou +1Language Model Generation Evaluation Rubric-Based Evaluation
Tsinghua University · King’s College London · University of Illinois Urbana-Champaign
FinAutoRubric: Expert-Guided Automatic Rubric Generation for Evaluating Financial Research Agents
Sep 28, 2026Hoyoung Lee, Suyeol Yun, Jack Haverty +17Automatic Rubric Generation LLM Agent Evaluation
LinqAlpha · UNIST · MassMutual Life Insurance +9
Rubric-Aware On-Policy Self-Distillation for LLM Personalization
Sep 28, 2026Yilun Qiu, Xiaoyan Zhao, Chengbing Wang +6LLM Personalization On-Policy Self-Distillation
Xiaohongshu Inc. · National University of Singapore · University of Science and Technology of China +1
RULER: Instance-aware Rubric Rewards for SVG Generation
Sep 21, 2026Hangyu Ran, Yuhao Zheng, Yingying Zhang +2Text-to-SVG Generation Vector Graphics Generation
Ant Group · The Hong Kong University of Science and Technology (Guangzhou) · Independent Researcher +1
From Transient Prompts to Persistent Control: Scientific Poster Generation via Recursive Semantic-Geometric Contracts
Sep 15, 2026Runze Li, Yukun Zhao, Can Xu +5Rubric-Guided Generation AI-Assisted Scientific Research
Baidu Inc., Beijing, China · Harbin University of Science and Technology, Harbin, China · Shandong University, Jinan, China +2
PaperGym: Rubric-Centered Evolution for Research-Plan Generation
Aug 31, 2026Yuhan Wang, Zhengxi Lu, Yuchen Yan +6AI Agents for Scientific Discovery Rubric-Based RL
Zhejiang University · Apple
Learning to Evaluate Before Improving: Automatic Rubric Induction for Automatic Research Agents
Aug 31, 2026Xuehai Wang, Haowei Qin, Tongxin Liu +6Automatic Rubric Generation AI Agent Evaluation
1Zhejiang University · University of Electronic Science and Technology of China · 3Beijing University of Posts and Telecommunications +1
GenRubric: Self-Evolving Rubric Generation for Scalable LLM Evaluation
Aug 30, 2026Yifan Chen, Haitao Li, Qingyao Ai +4LLM-as-a-Judge Language Model Generation Evaluation
Department of Computer Science and Technology, Tsinghua University · National University of Singapore
A Unified Framework to Elicit Structured Feedback for Interpretable Multi-Trait Essay Scoring
Aug 28, 2026Shihang Yang, Sanwoo Lee, Ningning Zhao +1Automated Essay Scoring Rubric-Guided Generation
National Key Laboratory for Multimedia Information Processing, Peking University · School of Computer Science, Peking University · School of Chinese Language and Literature, Beijing Normal University
Design the Feedback, Not Just the Reward: Environments for Open-Ended Reinforcement Learning
Aug 28, 2026Rui Jin, Jikai Chen, Chengyue Yu +7RL for Code Generation Code Generation
Inclusion AI, Ant Group · Zhongnan University
Rubrics as Visual-Repair Context for Self-Evolving UI-to-Code Generation
Aug 25, 2026Tianyi Xiong, Zhengyuan Yang, Xiaofei Wang +10Code Generation LLM Self-Refinement
University of Maryland, College Park · Microsoft
Rubric Dropout: A Simple Way to Mitigate Reward Hacking in Rubric-Based RL
Aug 12, 2026Minglai Yang, Xinyu Guo, Zhengliang Shi +8Reward Hacking Rubric-Based RL
Scale AI · University of Arizona · Carnegie Mellon University +2
ConRub-Med: Reinforcement Learning with Consensus Rubrics for Open-Ended Medical Question Answering
Aug 11, 2026Taojie Zhu, Yuan Xia, Tao Sun +8Rubric-Based RL Medical QA
Tsinghua University · Ant Group · Zhejiang University
RISE-RL: Rubric-Informed Selective Exploration for Open-Ended Reinforcement Learning
Aug 10, 2026Jinkun Hou, Zhuo Liu, Huimin Ren +3Open-Ended Generation RL for Language Models
1Peking University · 2Beijing Institute of Technology · 3Li Auto Inc.
Rubrics as Privileged Information for Open-Ended Generation
Aug 3, 2026Deepika Bablani, Ajay Gupta, Wanming ChenOpen-Ended Generation Rubric-Based Evaluation
Apple
CriPO: Enhancing Rubric-based RL via Self-Distillation
Jul 20, 2026Mingxuan Xia, Yuhang Yang, Chao Ye +7Credit Assignment in RL Rubric-Based RL
Zhejiang University · ByteDance
Can LLMs Write Reliable Rubrics? A Meta-Evaluation for Experiment Reproduction
Jul 14, 2026Hanhua Hong, Yizhi Li, Jiaoyan Chen +4LLM Evaluation Rubric-Based Evaluation
The University of Manchester · IQuest Research · University of Information Technology, VNU +2
FinResearchBench II: A Deep Research Benchmark with Consensus-Derived Gold Rubrics for Distinguishing Financial Report Quality
Jul 14, 2026Beidi Luan, Rui Sun, Sinuo Wang +5LLM-as-a-Judge Rubric-Based Evaluation
1StepFun · University of Adelaide · 2FinStep +1
EvoRubrics: Dynamic Rubrics as Rewards via Adversarial Co-Evolution for LLM Reinforcement Learning
Jun 22, 2026Hongxin Ding, Baixiang Huang, Yue Fang +6Automatic Rubric Generation RL for Language Models
National Engineering Research Center of Software Engineering, Peking University, China · School of Computer Science, Peking University, Beijing, China · Key Laboratory of High Confidence Software Technologies, Ministry of Education +2
DEEPRUBRIC: Evidence-Tree Rubric Supervision for Efficient Reinforcement Learning of Deep Research Agents
Jun 15, 2026Minghang Zhu, Chuyang Wei, Junhao Xu +3Deep Research Agents Rubric-Based RL
Shandong University, Qingdao, China · Zhongguancun Academy, Beijing, China · Fudan University, Shanghai, China
Rubric-Guided Self-Distillation: Post-Training Without Rubric Verifiers
Jun 10, 2026MohammadHossein Rezaei, Anas Mahmoud, Zihao Wang +6Rubric-Based RL Language Model Distillation
Scale AI
Support Vector Rubrics: Closing the Gap Between Self-Generated and Human Rubrics
Jun 6, 2026Mengyuan Sun, Yu Li, Zhuohao Yu +2Reward Modeling Preference Modeling
National Engineering Research Center for Software Engineering, Peking University · University of Science and Technology of China
Deep Research as Rubric for Reinforcement Learning
May 31, 2026Wangyi Mei, Zhouhong Gu, Zhenhan Bai +9Reward Design for RL Open-Ended Generation
Fudan University · Xiaohongshu Inc. · Beijing University of Posts and Telecommunications
EvoRubric: Self-Evolving Rubric-Driven RL for Open-Ended Generation
May 28, 2026Xin Guan, Xiaomeng Hu, Shen Huang +6Open-Ended Generation RL for Language Models
Tongyi Lab, Alibaba Group
Tournament-GRPO: Group-Wise Tournament Rewards for Reinforcement Learning in Open-Ended Long-Form Generation
May 26, 2026Zixuan Yang, Yiqun Chen, Wei Yang +7Open-Ended Generation Reward Modeling
Renmin University of China · University of Southern California · Zhejiang University +1
Co-ReAct: Rubrics as Step-Level Collaborators for ReAct Agents
May 22, 2026Jiazheng Kang, Bowen Zhang, Zixin Song +4Deep Research Agents Agentic Reasoning
Qwen Applications Business Group of Alibaba · Tsinghua University

Oct 21, 2026J/K move · Enter open · S save

RubricOpt: Self-Revision of Semantic Rubrics for Preference Optimization

Wei Chen, Yubing Wu, Shigui Li, Delu Zeng+6

South China University of Technology · LinkSprite · University of Waterloo

Rubric-Guided Generation Preference Optimization Automatic Rubric Generation

Open paper AskPDF arXiv

A model's failures can reveal gaps in the behavioral criteria guiding its training. We introduce RubricOpt, a framework that lets a policy revise these criteria within preference optimization. The policy diagnoses its own rubric-free outputs, retains requirements already covered by the rubric, and edits clauses that leave recurring failures unaddressed. A shared semantic representation connects task demands, preference-data contrasts, and rubric clauses, while a deterministic gate checks evidence references and fixed semantic anchors. The rubric then guides Direct Preference Optimization (DPO) during training, with preference pairs, labels, and the objective held fixed, and is removed at evaluation. Our analysis relates the local effect on rubric-free success to semantic alignment and a residual beyond the measured factors. Experiments on capability and open-ended generation benchmarks show that rubric conditioning can improve outcomes over ordinary DPO, with gains and regressions varying across models and datasets. A matched continuation isolates the contribution of revision from additional training and finds mixed incremental effects for the tested edit, whose feedback overlaps the evaluation set. RubricOpt thus brings the behavioral specification itself into the policy's feedback loop.